arXiv AI October 19, 2026 By Malavika Suresh, Rahaf Aljundi, Ikechukwu Nkisi-Orji, Nirmalie Wiratunga

Cross-Layer Attention Probing for Fine-Grained Hallucination Detection

Cross-Layer Attention Probing (CLAP) is a new activation‑probing method that examines the entire residual stream of Large Language Models (LLMs) to detect hallucinations. Experiments on five LLMs across three tasks demonstrate that CLAP outperforms baseline detectors for both greedy and temperature‑sampled outputs, enabling fine‑grained discrimination between hallucinated and non‑hallucinated responses. The approach also supports a detect‑then‑mitigate strategy that reduces hallucinations and maintains reliability even on out‑of‑distribution data.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jun 29

From Signals to Transfer: A Factorised Study of Probe-Based Uncertainty Estimation in Large Language Models

arXiv:2606. 27679v1 Announce Type: cross Abstract: Probe-based uncertainty estimation (UE) has emerged as a prominent approach to detect hallucinations in Large Language Models (LLMs) by learning uncertainty from internal model signals.

By Ponhvoan Srey, Xiaobao Wu, Cong-Duy Nguyen, Quang Minh Nguyen, Duc Anh Vu, Anh Tuan Luu

llms benchmarks safety

arXiv Machine Learning

Aug 4

Attention Sinks as Internal Signals for Hallucination Detection in Large Language Models

arXiv:2604. 10697v2 Announce Type: replace-cross Abstract: Large language models frequently exhibit hallucinations: fluent and confident outputs that are factually incorrect or unsupported by the input context.

By Jakub Binkowski, Kamil Adamczewski, Tomasz Kajdanowicz

llms benchmarks safety

Hugging Face Trending Papers

Jun 23

Grad Detect: Gradient-Based Hallucination Detection in LLMs

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse tasks, yet they remain prone to generating hallucinations. Detecting these hallucinations is critical for deploying LLMs reliably in high-stakes applications.

llms benchmarks safety

arXiv AI

Jun 24

Grad Detect: Gradient-Based Hallucination Detection in LLMs

arXiv:2606. 24790v1 Announce Type: cross Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse tasks, yet they remain prone to generating hallucinations.

By Anand Kamat, Daniel Blake, Brent M. Werness

llms benchmarks safety

arXiv AI

Jun 3

Automatic Layer Selection for Hallucination Detection

arXiv:2605. 26366v3 Announce Type: replace Abstract: Recent studies on hallucination detection have shown that hallucination-related signals are more strongly encoded in intermediate layers than in the final layer of large language models (LLMs).

By Xinpeng Wang, William X. Cao, Andrew Gordon Wilson, Zhe Zeng

llms nlp benchmarks safety

arXiv AI

Aug 11

Prompt Embedding Probes (PEP): Hallucination Detection in LLMs from Hidden States

arXiv:2608. 08024v1 Announce Type: cross Abstract: Large language models (LLMs) can generate fluent and useful responses but remain prone to hallucinations.

By Zakhar Mrykhin, Valentin Malykh

llms rag safety

One email a morning, machine-written

Related stories

From Signals to Transfer: A Factorised Study of Probe-Based Uncertainty Estimation in Large Language Models

Attention Sinks as Internal Signals for Hallucination Detection in Large Language Models

Grad Detect: Gradient-Based Hallucination Detection in LLMs

Grad Detect: Gradient-Based Hallucination Detection in LLMs

Automatic Layer Selection for Hallucination Detection

Prompt Embedding Probes (PEP): Hallucination Detection in LLMs from Hidden States